| { | |
| "best_metric": 0.7847222222222222, | |
| "best_model_checkpoint": "microsoft-resnet-50-cartoon-face-recognition/checkpoint-690", | |
| "epoch": 119.88888888888889, | |
| "global_step": 720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.037037037037037035, | |
| "eval_f1": 0.009802215531382198, | |
| "eval_loss": 3.177427053451538, | |
| "eval_precision": 0.006871793330126662, | |
| "eval_recall": 0.037037037037037035, | |
| "eval_runtime": 6.7511, | |
| "eval_samples_per_second": 63.989, | |
| "eval_steps_per_second": 1.037, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 3.4185, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_accuracy": 0.03009259259259259, | |
| "eval_f1": 0.012595532039976485, | |
| "eval_loss": 3.173919677734375, | |
| "eval_precision": 0.009991865408265568, | |
| "eval_recall": 0.03009259259259259, | |
| "eval_runtime": 5.4893, | |
| "eval_samples_per_second": 78.698, | |
| "eval_steps_per_second": 1.275, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_accuracy": 0.04398148148148148, | |
| "eval_f1": 0.03396177939075919, | |
| "eval_loss": 3.1668288707733154, | |
| "eval_precision": 0.08045697418202408, | |
| "eval_recall": 0.04398148148148148, | |
| "eval_runtime": 5.6812, | |
| "eval_samples_per_second": 76.04, | |
| "eval_steps_per_second": 1.232, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.6463, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "eval_accuracy": 0.037037037037037035, | |
| "eval_f1": 0.015118236629864536, | |
| "eval_loss": 3.158271312713623, | |
| "eval_precision": 0.018042564247921392, | |
| "eval_recall": 0.037037037037037035, | |
| "eval_runtime": 5.1688, | |
| "eval_samples_per_second": 83.579, | |
| "eval_steps_per_second": 1.354, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3899, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "eval_accuracy": 0.07407407407407407, | |
| "eval_f1": 0.04528877134769999, | |
| "eval_loss": 3.142496109008789, | |
| "eval_precision": 0.06098814150284739, | |
| "eval_recall": 0.07407407407407407, | |
| "eval_runtime": 5.4398, | |
| "eval_samples_per_second": 79.415, | |
| "eval_steps_per_second": 1.287, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "eval_accuracy": 0.08564814814814815, | |
| "eval_f1": 0.040453657257170324, | |
| "eval_loss": 3.1262054443359375, | |
| "eval_precision": 0.03336711386173307, | |
| "eval_recall": 0.08564814814814815, | |
| "eval_runtime": 5.1611, | |
| "eval_samples_per_second": 83.702, | |
| "eval_steps_per_second": 1.356, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.5947, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "eval_accuracy": 0.10185185185185185, | |
| "eval_f1": 0.04813087748076705, | |
| "eval_loss": 3.105499744415283, | |
| "eval_precision": 0.07837275882119042, | |
| "eval_recall": 0.10185185185185185, | |
| "eval_runtime": 5.3163, | |
| "eval_samples_per_second": 81.26, | |
| "eval_steps_per_second": 1.317, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "eval_accuracy": 0.11805555555555555, | |
| "eval_f1": 0.05001316779776901, | |
| "eval_loss": 3.0840911865234375, | |
| "eval_precision": 0.10709469464505224, | |
| "eval_recall": 0.11805555555555555, | |
| "eval_runtime": 5.3088, | |
| "eval_samples_per_second": 81.374, | |
| "eval_steps_per_second": 1.319, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 8.333333333333333e-05, | |
| "loss": 3.5553, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "eval_accuracy": 0.10648148148148148, | |
| "eval_f1": 0.034321942911473204, | |
| "eval_loss": 3.0650484561920166, | |
| "eval_precision": 0.021575460554167175, | |
| "eval_recall": 0.10648148148148148, | |
| "eval_runtime": 5.2915, | |
| "eval_samples_per_second": 81.641, | |
| "eval_steps_per_second": 1.323, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2713, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "eval_accuracy": 0.12731481481481483, | |
| "eval_f1": 0.04184436999619006, | |
| "eval_loss": 3.0350887775421143, | |
| "eval_precision": 0.03231738683127571, | |
| "eval_recall": 0.12731481481481483, | |
| "eval_runtime": 5.315, | |
| "eval_samples_per_second": 81.279, | |
| "eval_steps_per_second": 1.317, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "eval_accuracy": 0.12268518518518519, | |
| "eval_f1": 0.03896546460633453, | |
| "eval_loss": 3.006906747817993, | |
| "eval_precision": 0.031055780240739028, | |
| "eval_recall": 0.12268518518518519, | |
| "eval_runtime": 5.3282, | |
| "eval_samples_per_second": 81.078, | |
| "eval_steps_per_second": 1.314, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 0.00011666666666666667, | |
| "loss": 3.4382, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "eval_accuracy": 0.12037037037037036, | |
| "eval_f1": 0.03664636838867146, | |
| "eval_loss": 2.9754226207733154, | |
| "eval_precision": 0.035322359396433474, | |
| "eval_recall": 0.12037037037037036, | |
| "eval_runtime": 5.2664, | |
| "eval_samples_per_second": 82.029, | |
| "eval_steps_per_second": 1.329, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "eval_accuracy": 0.12268518518518519, | |
| "eval_f1": 0.03383682152179769, | |
| "eval_loss": 2.945517063140869, | |
| "eval_precision": 0.022390870365422862, | |
| "eval_recall": 0.12268518518518519, | |
| "eval_runtime": 5.4645, | |
| "eval_samples_per_second": 79.056, | |
| "eval_steps_per_second": 1.281, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 13.3, | |
| "learning_rate": 0.00011851851851851852, | |
| "loss": 3.3573, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "eval_accuracy": 0.12037037037037036, | |
| "eval_f1": 0.03316178047360843, | |
| "eval_loss": 2.9167439937591553, | |
| "eval_precision": 0.021296296296296296, | |
| "eval_recall": 0.12037037037037036, | |
| "eval_runtime": 5.6677, | |
| "eval_samples_per_second": 76.222, | |
| "eval_steps_per_second": 1.235, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 0.00011666666666666667, | |
| "loss": 3.0549, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "eval_accuracy": 0.12268518518518519, | |
| "eval_f1": 0.04084263761775177, | |
| "eval_loss": 2.884087562561035, | |
| "eval_precision": 0.047443229428523546, | |
| "eval_recall": 0.12268518518518519, | |
| "eval_runtime": 5.2214, | |
| "eval_samples_per_second": 82.737, | |
| "eval_steps_per_second": 1.341, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 15.89, | |
| "eval_accuracy": 0.1412037037037037, | |
| "eval_f1": 0.05401596739565727, | |
| "eval_loss": 2.8534481525421143, | |
| "eval_precision": 0.11735631001371744, | |
| "eval_recall": 0.1412037037037037, | |
| "eval_runtime": 5.2992, | |
| "eval_samples_per_second": 81.521, | |
| "eval_steps_per_second": 1.321, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 16.59, | |
| "learning_rate": 0.00011481481481481482, | |
| "loss": 3.1853, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "eval_accuracy": 0.15046296296296297, | |
| "eval_f1": 0.0666910894416082, | |
| "eval_loss": 2.814347743988037, | |
| "eval_precision": 0.15945772593650578, | |
| "eval_recall": 0.15046296296296297, | |
| "eval_runtime": 5.2953, | |
| "eval_samples_per_second": 81.581, | |
| "eval_steps_per_second": 1.322, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 17.89, | |
| "eval_accuracy": 0.16666666666666666, | |
| "eval_f1": 0.07186374965273062, | |
| "eval_loss": 2.777080774307251, | |
| "eval_precision": 0.16930278149907305, | |
| "eval_recall": 0.16666666666666666, | |
| "eval_runtime": 5.5347, | |
| "eval_samples_per_second": 78.053, | |
| "eval_steps_per_second": 1.265, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 18.3, | |
| "learning_rate": 0.00011296296296296296, | |
| "loss": 3.0871, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.89, | |
| "eval_accuracy": 0.17592592592592593, | |
| "eval_f1": 0.08963216187544253, | |
| "eval_loss": 2.7399983406066895, | |
| "eval_precision": 0.14542306534176452, | |
| "eval_recall": 0.17592592592592593, | |
| "eval_runtime": 6.4855, | |
| "eval_samples_per_second": 66.61, | |
| "eval_steps_per_second": 1.079, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 2.7666, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "eval_accuracy": 0.2013888888888889, | |
| "eval_f1": 0.10508380061910785, | |
| "eval_loss": 2.7047784328460693, | |
| "eval_precision": 0.0926529909484455, | |
| "eval_recall": 0.2013888888888889, | |
| "eval_runtime": 5.1825, | |
| "eval_samples_per_second": 83.357, | |
| "eval_steps_per_second": 1.351, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 20.89, | |
| "eval_accuracy": 0.23148148148148148, | |
| "eval_f1": 0.1249680097404455, | |
| "eval_loss": 2.6457977294921875, | |
| "eval_precision": 0.16220180035223264, | |
| "eval_recall": 0.23148148148148148, | |
| "eval_runtime": 5.3605, | |
| "eval_samples_per_second": 80.59, | |
| "eval_steps_per_second": 1.306, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 21.59, | |
| "learning_rate": 0.00010925925925925926, | |
| "loss": 2.846, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 21.89, | |
| "eval_accuracy": 0.2569444444444444, | |
| "eval_f1": 0.14696483781924097, | |
| "eval_loss": 2.5803465843200684, | |
| "eval_precision": 0.23855676187019514, | |
| "eval_recall": 0.2569444444444444, | |
| "eval_runtime": 5.1688, | |
| "eval_samples_per_second": 83.579, | |
| "eval_steps_per_second": 1.354, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 22.89, | |
| "eval_accuracy": 0.2638888888888889, | |
| "eval_f1": 0.15231614141660005, | |
| "eval_loss": 2.529054641723633, | |
| "eval_precision": 0.2724892697099823, | |
| "eval_recall": 0.2638888888888889, | |
| "eval_runtime": 5.3151, | |
| "eval_samples_per_second": 81.279, | |
| "eval_steps_per_second": 1.317, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 23.3, | |
| "learning_rate": 0.00010740740740740741, | |
| "loss": 2.7428, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 23.89, | |
| "eval_accuracy": 0.28703703703703703, | |
| "eval_f1": 0.18105006076248228, | |
| "eval_loss": 2.491586685180664, | |
| "eval_precision": 0.211443025358476, | |
| "eval_recall": 0.28703703703703703, | |
| "eval_runtime": 5.2796, | |
| "eval_samples_per_second": 81.825, | |
| "eval_steps_per_second": 1.326, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 0.00010555555555555557, | |
| "loss": 2.4183, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "eval_accuracy": 0.30787037037037035, | |
| "eval_f1": 0.20479489700821343, | |
| "eval_loss": 2.427311658859253, | |
| "eval_precision": 0.23219427179632832, | |
| "eval_recall": 0.30787037037037035, | |
| "eval_runtime": 5.439, | |
| "eval_samples_per_second": 79.426, | |
| "eval_steps_per_second": 1.287, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 25.89, | |
| "eval_accuracy": 0.3194444444444444, | |
| "eval_f1": 0.22377035813767307, | |
| "eval_loss": 2.392331838607788, | |
| "eval_precision": 0.2936854089800938, | |
| "eval_recall": 0.3194444444444444, | |
| "eval_runtime": 5.5411, | |
| "eval_samples_per_second": 77.962, | |
| "eval_steps_per_second": 1.263, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 26.59, | |
| "learning_rate": 0.0001037037037037037, | |
| "loss": 2.5064, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 26.89, | |
| "eval_accuracy": 0.3402777777777778, | |
| "eval_f1": 0.24941517503564606, | |
| "eval_loss": 2.334895133972168, | |
| "eval_precision": 0.3182802115296284, | |
| "eval_recall": 0.3402777777777778, | |
| "eval_runtime": 5.4141, | |
| "eval_samples_per_second": 79.791, | |
| "eval_steps_per_second": 1.293, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 27.89, | |
| "eval_accuracy": 0.3541666666666667, | |
| "eval_f1": 0.2663498097031901, | |
| "eval_loss": 2.297736167907715, | |
| "eval_precision": 0.3553616134289536, | |
| "eval_recall": 0.3541666666666667, | |
| "eval_runtime": 6.6536, | |
| "eval_samples_per_second": 64.927, | |
| "eval_steps_per_second": 1.052, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 28.3, | |
| "learning_rate": 0.00010185185185185186, | |
| "loss": 2.4046, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "eval_accuracy": 0.3773148148148148, | |
| "eval_f1": 0.2980587048254368, | |
| "eval_loss": 2.236337661743164, | |
| "eval_precision": 0.3214024127386118, | |
| "eval_recall": 0.3773148148148148, | |
| "eval_runtime": 5.4904, | |
| "eval_samples_per_second": 78.683, | |
| "eval_steps_per_second": 1.275, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 29.89, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1201, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 29.89, | |
| "eval_accuracy": 0.3888888888888889, | |
| "eval_f1": 0.31791564865485733, | |
| "eval_loss": 2.179067611694336, | |
| "eval_precision": 0.40240237475373924, | |
| "eval_recall": 0.3888888888888889, | |
| "eval_runtime": 5.3714, | |
| "eval_samples_per_second": 80.425, | |
| "eval_steps_per_second": 1.303, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 30.89, | |
| "eval_accuracy": 0.41435185185185186, | |
| "eval_f1": 0.34551235135842745, | |
| "eval_loss": 2.1447603702545166, | |
| "eval_precision": 0.4079261289461761, | |
| "eval_recall": 0.41435185185185186, | |
| "eval_runtime": 5.3344, | |
| "eval_samples_per_second": 80.984, | |
| "eval_steps_per_second": 1.312, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 31.59, | |
| "learning_rate": 9.814814814814815e-05, | |
| "loss": 2.1705, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 31.89, | |
| "eval_accuracy": 0.4305555555555556, | |
| "eval_f1": 0.3583236278769072, | |
| "eval_loss": 2.0968592166900635, | |
| "eval_precision": 0.42138862813145966, | |
| "eval_recall": 0.4305555555555556, | |
| "eval_runtime": 5.2736, | |
| "eval_samples_per_second": 81.918, | |
| "eval_steps_per_second": 1.327, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 32.89, | |
| "eval_accuracy": 0.44675925925925924, | |
| "eval_f1": 0.3796832086663997, | |
| "eval_loss": 2.0535407066345215, | |
| "eval_precision": 0.44476509568042505, | |
| "eval_recall": 0.44675925925925924, | |
| "eval_runtime": 5.5334, | |
| "eval_samples_per_second": 78.071, | |
| "eval_steps_per_second": 1.265, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 33.3, | |
| "learning_rate": 9.62962962962963e-05, | |
| "loss": 2.0295, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 33.89, | |
| "eval_accuracy": 0.47453703703703703, | |
| "eval_f1": 0.41326930710155785, | |
| "eval_loss": 1.9940098524093628, | |
| "eval_precision": 0.487688116532901, | |
| "eval_recall": 0.47453703703703703, | |
| "eval_runtime": 5.2418, | |
| "eval_samples_per_second": 82.414, | |
| "eval_steps_per_second": 1.335, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 34.89, | |
| "learning_rate": 9.444444444444446e-05, | |
| "loss": 1.8114, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 34.89, | |
| "eval_accuracy": 0.4861111111111111, | |
| "eval_f1": 0.4260885563604569, | |
| "eval_loss": 1.9467288255691528, | |
| "eval_precision": 0.4952086854944768, | |
| "eval_recall": 0.4861111111111111, | |
| "eval_runtime": 6.2488, | |
| "eval_samples_per_second": 69.134, | |
| "eval_steps_per_second": 1.12, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 35.89, | |
| "eval_accuracy": 0.4930555555555556, | |
| "eval_f1": 0.43212988067709945, | |
| "eval_loss": 1.8896209001541138, | |
| "eval_precision": 0.4509807456365427, | |
| "eval_recall": 0.4930555555555556, | |
| "eval_runtime": 6.1753, | |
| "eval_samples_per_second": 69.957, | |
| "eval_steps_per_second": 1.134, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 36.59, | |
| "learning_rate": 9.259259259259259e-05, | |
| "loss": 1.8048, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 36.89, | |
| "eval_accuracy": 0.5046296296296297, | |
| "eval_f1": 0.4507112029285062, | |
| "eval_loss": 1.8403947353363037, | |
| "eval_precision": 0.4858612126346595, | |
| "eval_recall": 0.5046296296296297, | |
| "eval_runtime": 5.4983, | |
| "eval_samples_per_second": 78.57, | |
| "eval_steps_per_second": 1.273, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 37.89, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_f1": 0.48163822225958186, | |
| "eval_loss": 1.7998918294906616, | |
| "eval_precision": 0.5142116902603466, | |
| "eval_recall": 0.5277777777777778, | |
| "eval_runtime": 5.2197, | |
| "eval_samples_per_second": 82.764, | |
| "eval_steps_per_second": 1.341, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 38.3, | |
| "learning_rate": 9.074074074074075e-05, | |
| "loss": 1.6862, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 38.89, | |
| "eval_accuracy": 0.5324074074074074, | |
| "eval_f1": 0.48444518889171245, | |
| "eval_loss": 1.7363009452819824, | |
| "eval_precision": 0.5169324177278161, | |
| "eval_recall": 0.5324074074074074, | |
| "eval_runtime": 5.3984, | |
| "eval_samples_per_second": 80.023, | |
| "eval_steps_per_second": 1.297, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 39.89, | |
| "learning_rate": 8.888888888888888e-05, | |
| "loss": 1.4545, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 39.89, | |
| "eval_accuracy": 0.5439814814814815, | |
| "eval_f1": 0.4970594159719364, | |
| "eval_loss": 1.7104405164718628, | |
| "eval_precision": 0.5100423891967305, | |
| "eval_recall": 0.5439814814814815, | |
| "eval_runtime": 5.3694, | |
| "eval_samples_per_second": 80.456, | |
| "eval_steps_per_second": 1.304, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 40.89, | |
| "eval_accuracy": 0.5648148148148148, | |
| "eval_f1": 0.5137970884972636, | |
| "eval_loss": 1.6491522789001465, | |
| "eval_precision": 0.523917294193656, | |
| "eval_recall": 0.5648148148148148, | |
| "eval_runtime": 5.3928, | |
| "eval_samples_per_second": 80.107, | |
| "eval_steps_per_second": 1.298, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 41.59, | |
| "learning_rate": 8.703703703703704e-05, | |
| "loss": 1.4444, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 41.89, | |
| "eval_accuracy": 0.5671296296296297, | |
| "eval_f1": 0.5260280139698915, | |
| "eval_loss": 1.6076487302780151, | |
| "eval_precision": 0.5329085789061826, | |
| "eval_recall": 0.5671296296296297, | |
| "eval_runtime": 5.3158, | |
| "eval_samples_per_second": 81.268, | |
| "eval_steps_per_second": 1.317, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 42.89, | |
| "eval_accuracy": 0.5740740740740741, | |
| "eval_f1": 0.5423804527832623, | |
| "eval_loss": 1.5784292221069336, | |
| "eval_precision": 0.5708459252154017, | |
| "eval_recall": 0.5740740740740741, | |
| "eval_runtime": 5.2241, | |
| "eval_samples_per_second": 82.694, | |
| "eval_steps_per_second": 1.34, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 43.3, | |
| "learning_rate": 8.51851851851852e-05, | |
| "loss": 1.3124, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 43.89, | |
| "eval_accuracy": 0.6018518518518519, | |
| "eval_f1": 0.5618867514921587, | |
| "eval_loss": 1.5258712768554688, | |
| "eval_precision": 0.5977120457097308, | |
| "eval_recall": 0.6018518518518519, | |
| "eval_runtime": 5.4521, | |
| "eval_samples_per_second": 79.236, | |
| "eval_steps_per_second": 1.284, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 44.89, | |
| "learning_rate": 8.333333333333333e-05, | |
| "loss": 1.1645, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 44.89, | |
| "eval_accuracy": 0.6180555555555556, | |
| "eval_f1": 0.587977803961619, | |
| "eval_loss": 1.481404423713684, | |
| "eval_precision": 0.6033401199444866, | |
| "eval_recall": 0.6180555555555556, | |
| "eval_runtime": 5.2922, | |
| "eval_samples_per_second": 81.629, | |
| "eval_steps_per_second": 1.323, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 45.89, | |
| "eval_accuracy": 0.6087962962962963, | |
| "eval_f1": 0.5803382659924391, | |
| "eval_loss": 1.469708800315857, | |
| "eval_precision": 0.6033107779207628, | |
| "eval_recall": 0.6087962962962963, | |
| "eval_runtime": 5.3039, | |
| "eval_samples_per_second": 81.449, | |
| "eval_steps_per_second": 1.32, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 46.59, | |
| "learning_rate": 8.148148148148149e-05, | |
| "loss": 1.1307, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 46.89, | |
| "eval_accuracy": 0.6087962962962963, | |
| "eval_f1": 0.5768532160244407, | |
| "eval_loss": 1.4379969835281372, | |
| "eval_precision": 0.6014549575028018, | |
| "eval_recall": 0.6087962962962963, | |
| "eval_runtime": 5.4401, | |
| "eval_samples_per_second": 79.41, | |
| "eval_steps_per_second": 1.287, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 47.89, | |
| "eval_accuracy": 0.6226851851851852, | |
| "eval_f1": 0.5916934301381287, | |
| "eval_loss": 1.3872352838516235, | |
| "eval_precision": 0.6084938497179186, | |
| "eval_recall": 0.6226851851851852, | |
| "eval_runtime": 5.7913, | |
| "eval_samples_per_second": 74.594, | |
| "eval_steps_per_second": 1.209, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 48.3, | |
| "learning_rate": 7.962962962962962e-05, | |
| "loss": 1.0347, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 48.89, | |
| "eval_accuracy": 0.6157407407407407, | |
| "eval_f1": 0.5880203126612452, | |
| "eval_loss": 1.3708983659744263, | |
| "eval_precision": 0.6039183905119778, | |
| "eval_recall": 0.6157407407407407, | |
| "eval_runtime": 5.2614, | |
| "eval_samples_per_second": 82.107, | |
| "eval_steps_per_second": 1.33, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 49.89, | |
| "learning_rate": 7.777777777777778e-05, | |
| "loss": 0.8962, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 49.89, | |
| "eval_accuracy": 0.6296296296296297, | |
| "eval_f1": 0.605687298694788, | |
| "eval_loss": 1.341522455215454, | |
| "eval_precision": 0.612048881556709, | |
| "eval_recall": 0.6296296296296297, | |
| "eval_runtime": 5.311, | |
| "eval_samples_per_second": 81.34, | |
| "eval_steps_per_second": 1.318, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 50.89, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_f1": 0.613426108384686, | |
| "eval_loss": 1.3290259838104248, | |
| "eval_precision": 0.6327490606701418, | |
| "eval_recall": 0.6388888888888888, | |
| "eval_runtime": 5.2871, | |
| "eval_samples_per_second": 81.708, | |
| "eval_steps_per_second": 1.324, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 51.59, | |
| "learning_rate": 7.592592592592593e-05, | |
| "loss": 0.8898, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 51.89, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_f1": 0.6119123977370672, | |
| "eval_loss": 1.2836151123046875, | |
| "eval_precision": 0.6191504139826349, | |
| "eval_recall": 0.6388888888888888, | |
| "eval_runtime": 5.3703, | |
| "eval_samples_per_second": 80.442, | |
| "eval_steps_per_second": 1.303, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 52.89, | |
| "eval_accuracy": 0.6412037037037037, | |
| "eval_f1": 0.6162189940531424, | |
| "eval_loss": 1.2664588689804077, | |
| "eval_precision": 0.6185599459790397, | |
| "eval_recall": 0.6412037037037037, | |
| "eval_runtime": 5.3255, | |
| "eval_samples_per_second": 81.119, | |
| "eval_steps_per_second": 1.314, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 53.3, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.7886, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 53.89, | |
| "eval_accuracy": 0.6550925925925926, | |
| "eval_f1": 0.6318769738810363, | |
| "eval_loss": 1.2272124290466309, | |
| "eval_precision": 0.6430932223319198, | |
| "eval_recall": 0.6550925925925926, | |
| "eval_runtime": 6.4776, | |
| "eval_samples_per_second": 66.692, | |
| "eval_steps_per_second": 1.081, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 54.89, | |
| "learning_rate": 7.222222222222222e-05, | |
| "loss": 0.6794, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 54.89, | |
| "eval_accuracy": 0.6805555555555556, | |
| "eval_f1": 0.6628815346611416, | |
| "eval_loss": 1.2144430875778198, | |
| "eval_precision": 0.6643161507927962, | |
| "eval_recall": 0.6805555555555556, | |
| "eval_runtime": 5.3789, | |
| "eval_samples_per_second": 80.314, | |
| "eval_steps_per_second": 1.301, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 55.89, | |
| "eval_accuracy": 0.6805555555555556, | |
| "eval_f1": 0.6641541104251447, | |
| "eval_loss": 1.1816602945327759, | |
| "eval_precision": 0.6665719090253448, | |
| "eval_recall": 0.6805555555555556, | |
| "eval_runtime": 5.3081, | |
| "eval_samples_per_second": 81.385, | |
| "eval_steps_per_second": 1.319, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 56.59, | |
| "learning_rate": 7.037037037037038e-05, | |
| "loss": 0.6459, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 56.89, | |
| "eval_accuracy": 0.6782407407407407, | |
| "eval_f1": 0.6573948843052861, | |
| "eval_loss": 1.1702219247817993, | |
| "eval_precision": 0.6591247168593658, | |
| "eval_recall": 0.6782407407407407, | |
| "eval_runtime": 5.3756, | |
| "eval_samples_per_second": 80.363, | |
| "eval_steps_per_second": 1.302, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 57.89, | |
| "eval_accuracy": 0.7037037037037037, | |
| "eval_f1": 0.6882802756329267, | |
| "eval_loss": 1.0946831703186035, | |
| "eval_precision": 0.686333931300664, | |
| "eval_recall": 0.7037037037037037, | |
| "eval_runtime": 5.4261, | |
| "eval_samples_per_second": 79.615, | |
| "eval_steps_per_second": 1.29, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 58.3, | |
| "learning_rate": 6.851851851851852e-05, | |
| "loss": 0.6075, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 58.89, | |
| "eval_accuracy": 0.7037037037037037, | |
| "eval_f1": 0.6867332708223882, | |
| "eval_loss": 1.1226900815963745, | |
| "eval_precision": 0.6874024894506818, | |
| "eval_recall": 0.7037037037037037, | |
| "eval_runtime": 5.4706, | |
| "eval_samples_per_second": 78.968, | |
| "eval_steps_per_second": 1.28, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 59.89, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.4979, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 59.89, | |
| "eval_accuracy": 0.7083333333333334, | |
| "eval_f1": 0.6895357100839747, | |
| "eval_loss": 1.0848513841629028, | |
| "eval_precision": 0.6813335838104505, | |
| "eval_recall": 0.7083333333333334, | |
| "eval_runtime": 5.4609, | |
| "eval_samples_per_second": 79.108, | |
| "eval_steps_per_second": 1.282, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 60.89, | |
| "eval_accuracy": 0.7152777777777778, | |
| "eval_f1": 0.6976241288914542, | |
| "eval_loss": 1.0742223262786865, | |
| "eval_precision": 0.6924067070864097, | |
| "eval_recall": 0.7152777777777778, | |
| "eval_runtime": 5.4024, | |
| "eval_samples_per_second": 79.964, | |
| "eval_steps_per_second": 1.296, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 61.59, | |
| "learning_rate": 6.481481481481482e-05, | |
| "loss": 0.4895, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 61.89, | |
| "eval_accuracy": 0.7245370370370371, | |
| "eval_f1": 0.7056673305111377, | |
| "eval_loss": 1.0452089309692383, | |
| "eval_precision": 0.7020110351433776, | |
| "eval_recall": 0.7245370370370371, | |
| "eval_runtime": 5.2426, | |
| "eval_samples_per_second": 82.401, | |
| "eval_steps_per_second": 1.335, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 62.89, | |
| "eval_accuracy": 0.7361111111111112, | |
| "eval_f1": 0.7235022517584233, | |
| "eval_loss": 1.0434988737106323, | |
| "eval_precision": 0.7315692329774679, | |
| "eval_recall": 0.7361111111111112, | |
| "eval_runtime": 5.6115, | |
| "eval_samples_per_second": 76.984, | |
| "eval_steps_per_second": 1.247, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 63.3, | |
| "learning_rate": 6.296296296296296e-05, | |
| "loss": 0.456, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 63.89, | |
| "eval_accuracy": 0.6921296296296297, | |
| "eval_f1": 0.6782660667203742, | |
| "eval_loss": 1.0698424577713013, | |
| "eval_precision": 0.6835014015139541, | |
| "eval_recall": 0.6921296296296297, | |
| "eval_runtime": 5.1579, | |
| "eval_samples_per_second": 83.755, | |
| "eval_steps_per_second": 1.357, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 64.89, | |
| "learning_rate": 6.111111111111112e-05, | |
| "loss": 0.3816, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 64.89, | |
| "eval_accuracy": 0.7222222222222222, | |
| "eval_f1": 0.7090977646443078, | |
| "eval_loss": 1.012607455253601, | |
| "eval_precision": 0.7063543756769308, | |
| "eval_recall": 0.7222222222222222, | |
| "eval_runtime": 5.3628, | |
| "eval_samples_per_second": 80.554, | |
| "eval_steps_per_second": 1.305, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 65.89, | |
| "eval_accuracy": 0.7361111111111112, | |
| "eval_f1": 0.7204764875345293, | |
| "eval_loss": 0.993401825428009, | |
| "eval_precision": 0.724681390825583, | |
| "eval_recall": 0.7361111111111112, | |
| "eval_runtime": 5.6989, | |
| "eval_samples_per_second": 75.804, | |
| "eval_steps_per_second": 1.228, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 66.59, | |
| "learning_rate": 5.925925925925926e-05, | |
| "loss": 0.3599, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 66.89, | |
| "eval_accuracy": 0.7291666666666666, | |
| "eval_f1": 0.7170196751234628, | |
| "eval_loss": 0.9959847927093506, | |
| "eval_precision": 0.7213039734393419, | |
| "eval_recall": 0.7291666666666666, | |
| "eval_runtime": 5.2019, | |
| "eval_samples_per_second": 83.046, | |
| "eval_steps_per_second": 1.346, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 67.89, | |
| "eval_accuracy": 0.7222222222222222, | |
| "eval_f1": 0.7086739406130538, | |
| "eval_loss": 1.0140923261642456, | |
| "eval_precision": 0.714832297403849, | |
| "eval_recall": 0.7222222222222222, | |
| "eval_runtime": 5.4428, | |
| "eval_samples_per_second": 79.371, | |
| "eval_steps_per_second": 1.286, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 68.3, | |
| "learning_rate": 5.740740740740741e-05, | |
| "loss": 0.3484, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 68.89, | |
| "eval_accuracy": 0.7222222222222222, | |
| "eval_f1": 0.7106977986015407, | |
| "eval_loss": 0.9933716058731079, | |
| "eval_precision": 0.7124795295102475, | |
| "eval_recall": 0.7222222222222222, | |
| "eval_runtime": 5.4357, | |
| "eval_samples_per_second": 79.474, | |
| "eval_steps_per_second": 1.288, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 69.89, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.2939, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 69.89, | |
| "eval_accuracy": 0.7430555555555556, | |
| "eval_f1": 0.7348772075580454, | |
| "eval_loss": 0.9834648370742798, | |
| "eval_precision": 0.7417468353179321, | |
| "eval_recall": 0.7430555555555556, | |
| "eval_runtime": 5.6077, | |
| "eval_samples_per_second": 77.037, | |
| "eval_steps_per_second": 1.248, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 70.89, | |
| "eval_accuracy": 0.7314814814814815, | |
| "eval_f1": 0.7216822341228574, | |
| "eval_loss": 0.9870407581329346, | |
| "eval_precision": 0.7274511197247954, | |
| "eval_recall": 0.7314814814814815, | |
| "eval_runtime": 5.4574, | |
| "eval_samples_per_second": 79.159, | |
| "eval_steps_per_second": 1.283, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 71.59, | |
| "learning_rate": 5.3703703703703704e-05, | |
| "loss": 0.285, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 71.89, | |
| "eval_accuracy": 0.7430555555555556, | |
| "eval_f1": 0.733989971528034, | |
| "eval_loss": 0.9656376242637634, | |
| "eval_precision": 0.741147872977627, | |
| "eval_recall": 0.7430555555555556, | |
| "eval_runtime": 5.203, | |
| "eval_samples_per_second": 83.03, | |
| "eval_steps_per_second": 1.345, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 72.89, | |
| "eval_accuracy": 0.7337962962962963, | |
| "eval_f1": 0.7266736305881797, | |
| "eval_loss": 0.9461933970451355, | |
| "eval_precision": 0.7320442158992043, | |
| "eval_recall": 0.7337962962962963, | |
| "eval_runtime": 8.4768, | |
| "eval_samples_per_second": 50.963, | |
| "eval_steps_per_second": 0.826, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 73.3, | |
| "learning_rate": 5.185185185185185e-05, | |
| "loss": 0.2463, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 73.89, | |
| "eval_accuracy": 0.7453703703703703, | |
| "eval_f1": 0.7384341548610988, | |
| "eval_loss": 0.9513481855392456, | |
| "eval_precision": 0.7467304556246889, | |
| "eval_recall": 0.7453703703703703, | |
| "eval_runtime": 5.2401, | |
| "eval_samples_per_second": 82.442, | |
| "eval_steps_per_second": 1.336, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 74.89, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2328, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 74.89, | |
| "eval_accuracy": 0.7361111111111112, | |
| "eval_f1": 0.7285971835253146, | |
| "eval_loss": 0.9334164261817932, | |
| "eval_precision": 0.7389054794152377, | |
| "eval_recall": 0.7361111111111112, | |
| "eval_runtime": 5.3561, | |
| "eval_samples_per_second": 80.656, | |
| "eval_steps_per_second": 1.307, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 75.89, | |
| "eval_accuracy": 0.7384259259259259, | |
| "eval_f1": 0.7291154917372571, | |
| "eval_loss": 0.9375342130661011, | |
| "eval_precision": 0.7278364301205459, | |
| "eval_recall": 0.7384259259259259, | |
| "eval_runtime": 5.6458, | |
| "eval_samples_per_second": 76.516, | |
| "eval_steps_per_second": 1.24, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 76.59, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.2208, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 76.89, | |
| "eval_accuracy": 0.7407407407407407, | |
| "eval_f1": 0.7321580282679521, | |
| "eval_loss": 0.9331722855567932, | |
| "eval_precision": 0.7356617662856251, | |
| "eval_recall": 0.7407407407407407, | |
| "eval_runtime": 5.6602, | |
| "eval_samples_per_second": 76.322, | |
| "eval_steps_per_second": 1.237, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 77.89, | |
| "eval_accuracy": 0.7384259259259259, | |
| "eval_f1": 0.7345507865669115, | |
| "eval_loss": 0.9407795071601868, | |
| "eval_precision": 0.740572946269861, | |
| "eval_recall": 0.7384259259259259, | |
| "eval_runtime": 6.1079, | |
| "eval_samples_per_second": 70.728, | |
| "eval_steps_per_second": 1.146, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 78.3, | |
| "learning_rate": 4.6296296296296294e-05, | |
| "loss": 0.2177, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 78.89, | |
| "eval_accuracy": 0.7222222222222222, | |
| "eval_f1": 0.713643812457414, | |
| "eval_loss": 0.9059470891952515, | |
| "eval_precision": 0.7182721947191242, | |
| "eval_recall": 0.7222222222222222, | |
| "eval_runtime": 5.5576, | |
| "eval_samples_per_second": 77.731, | |
| "eval_steps_per_second": 1.26, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 79.89, | |
| "learning_rate": 4.444444444444444e-05, | |
| "loss": 0.1734, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 79.89, | |
| "eval_accuracy": 0.7314814814814815, | |
| "eval_f1": 0.7256550902066806, | |
| "eval_loss": 0.9517382383346558, | |
| "eval_precision": 0.7371182560572754, | |
| "eval_recall": 0.7314814814814815, | |
| "eval_runtime": 5.7365, | |
| "eval_samples_per_second": 75.308, | |
| "eval_steps_per_second": 1.22, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 80.89, | |
| "eval_accuracy": 0.7523148148148148, | |
| "eval_f1": 0.7423879522381177, | |
| "eval_loss": 0.9062556624412537, | |
| "eval_precision": 0.7462328400927609, | |
| "eval_recall": 0.7523148148148148, | |
| "eval_runtime": 5.6093, | |
| "eval_samples_per_second": 77.015, | |
| "eval_steps_per_second": 1.248, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 81.59, | |
| "learning_rate": 4.25925925925926e-05, | |
| "loss": 0.1791, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 81.89, | |
| "eval_accuracy": 0.7453703703703703, | |
| "eval_f1": 0.7386111806656375, | |
| "eval_loss": 0.9171371459960938, | |
| "eval_precision": 0.7460586842065221, | |
| "eval_recall": 0.7453703703703703, | |
| "eval_runtime": 6.3994, | |
| "eval_samples_per_second": 67.506, | |
| "eval_steps_per_second": 1.094, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 82.89, | |
| "eval_accuracy": 0.7523148148148148, | |
| "eval_f1": 0.7485400201597975, | |
| "eval_loss": 0.8845748901367188, | |
| "eval_precision": 0.7561086436421744, | |
| "eval_recall": 0.7523148148148148, | |
| "eval_runtime": 5.4558, | |
| "eval_samples_per_second": 79.181, | |
| "eval_steps_per_second": 1.283, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 83.3, | |
| "learning_rate": 4.0740740740740745e-05, | |
| "loss": 0.1681, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 83.89, | |
| "eval_accuracy": 0.7384259259259259, | |
| "eval_f1": 0.732043113565851, | |
| "eval_loss": 0.8870928883552551, | |
| "eval_precision": 0.743089114195319, | |
| "eval_recall": 0.7384259259259259, | |
| "eval_runtime": 5.6826, | |
| "eval_samples_per_second": 76.021, | |
| "eval_steps_per_second": 1.232, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 84.89, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1573, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 84.89, | |
| "eval_accuracy": 0.7453703703703703, | |
| "eval_f1": 0.7394662768116576, | |
| "eval_loss": 0.9117562174797058, | |
| "eval_precision": 0.7473985610054007, | |
| "eval_recall": 0.7453703703703703, | |
| "eval_runtime": 5.7055, | |
| "eval_samples_per_second": 75.717, | |
| "eval_steps_per_second": 1.227, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 85.89, | |
| "eval_accuracy": 0.7407407407407407, | |
| "eval_f1": 0.7365532820392154, | |
| "eval_loss": 0.9005970358848572, | |
| "eval_precision": 0.7431722449551572, | |
| "eval_recall": 0.7407407407407407, | |
| "eval_runtime": 5.5008, | |
| "eval_samples_per_second": 78.534, | |
| "eval_steps_per_second": 1.273, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 86.59, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.1439, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 86.89, | |
| "eval_accuracy": 0.7615740740740741, | |
| "eval_f1": 0.7579475458895545, | |
| "eval_loss": 0.8702595829963684, | |
| "eval_precision": 0.7692736377187624, | |
| "eval_recall": 0.7615740740740741, | |
| "eval_runtime": 5.4161, | |
| "eval_samples_per_second": 79.762, | |
| "eval_steps_per_second": 1.292, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 87.89, | |
| "eval_accuracy": 0.7453703703703703, | |
| "eval_f1": 0.7400568258235957, | |
| "eval_loss": 0.8988061547279358, | |
| "eval_precision": 0.756961704237031, | |
| "eval_recall": 0.7453703703703703, | |
| "eval_runtime": 6.1896, | |
| "eval_samples_per_second": 69.795, | |
| "eval_steps_per_second": 1.131, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 88.3, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.1362, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 88.89, | |
| "eval_accuracy": 0.7453703703703703, | |
| "eval_f1": 0.7395910859987699, | |
| "eval_loss": 0.9234440326690674, | |
| "eval_precision": 0.7476805026036663, | |
| "eval_recall": 0.7453703703703703, | |
| "eval_runtime": 5.5214, | |
| "eval_samples_per_second": 78.241, | |
| "eval_steps_per_second": 1.268, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 89.89, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1249, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 89.89, | |
| "eval_accuracy": 0.75, | |
| "eval_f1": 0.7425364320908299, | |
| "eval_loss": 0.8859997391700745, | |
| "eval_precision": 0.7472920891857668, | |
| "eval_recall": 0.75, | |
| "eval_runtime": 5.5446, | |
| "eval_samples_per_second": 77.914, | |
| "eval_steps_per_second": 1.262, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 90.89, | |
| "eval_accuracy": 0.7546296296296297, | |
| "eval_f1": 0.7513210643679686, | |
| "eval_loss": 0.8607540726661682, | |
| "eval_precision": 0.7600931860627275, | |
| "eval_recall": 0.7546296296296297, | |
| "eval_runtime": 5.3436, | |
| "eval_samples_per_second": 80.844, | |
| "eval_steps_per_second": 1.31, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 91.59, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.1264, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 91.89, | |
| "eval_accuracy": 0.7592592592592593, | |
| "eval_f1": 0.755976727084107, | |
| "eval_loss": 0.8870556950569153, | |
| "eval_precision": 0.7639504307480309, | |
| "eval_recall": 0.7592592592592593, | |
| "eval_runtime": 5.4043, | |
| "eval_samples_per_second": 79.937, | |
| "eval_steps_per_second": 1.295, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 92.89, | |
| "eval_accuracy": 0.7638888888888888, | |
| "eval_f1": 0.7599096471224447, | |
| "eval_loss": 0.8431653380393982, | |
| "eval_precision": 0.7726915475071081, | |
| "eval_recall": 0.7638888888888888, | |
| "eval_runtime": 5.4755, | |
| "eval_samples_per_second": 78.897, | |
| "eval_steps_per_second": 1.278, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 93.3, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.1201, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 93.89, | |
| "eval_accuracy": 0.7638888888888888, | |
| "eval_f1": 0.7568888380506066, | |
| "eval_loss": 0.8654246926307678, | |
| "eval_precision": 0.7697564792814707, | |
| "eval_recall": 0.7638888888888888, | |
| "eval_runtime": 6.2851, | |
| "eval_samples_per_second": 68.734, | |
| "eval_steps_per_second": 1.114, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 94.89, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1117, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 94.89, | |
| "eval_accuracy": 0.7453703703703703, | |
| "eval_f1": 0.741519942517561, | |
| "eval_loss": 0.8856301307678223, | |
| "eval_precision": 0.7568693783641538, | |
| "eval_recall": 0.7453703703703703, | |
| "eval_runtime": 5.3442, | |
| "eval_samples_per_second": 80.835, | |
| "eval_steps_per_second": 1.31, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 95.89, | |
| "eval_accuracy": 0.7546296296296297, | |
| "eval_f1": 0.7535192525414777, | |
| "eval_loss": 0.8668476939201355, | |
| "eval_precision": 0.7686452769477832, | |
| "eval_recall": 0.7546296296296297, | |
| "eval_runtime": 5.3944, | |
| "eval_samples_per_second": 80.082, | |
| "eval_steps_per_second": 1.298, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 96.59, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.1128, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 96.89, | |
| "eval_accuracy": 0.7662037037037037, | |
| "eval_f1": 0.7618510413877603, | |
| "eval_loss": 0.8629916310310364, | |
| "eval_precision": 0.7697577256793718, | |
| "eval_recall": 0.7662037037037037, | |
| "eval_runtime": 5.4335, | |
| "eval_samples_per_second": 79.506, | |
| "eval_steps_per_second": 1.288, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 97.89, | |
| "eval_accuracy": 0.7731481481481481, | |
| "eval_f1": 0.7696239297314015, | |
| "eval_loss": 0.8551383018493652, | |
| "eval_precision": 0.7826245726036102, | |
| "eval_recall": 0.7731481481481481, | |
| "eval_runtime": 5.1954, | |
| "eval_samples_per_second": 83.151, | |
| "eval_steps_per_second": 1.347, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 98.3, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.1155, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 98.89, | |
| "eval_accuracy": 0.7708333333333334, | |
| "eval_f1": 0.7643091084212846, | |
| "eval_loss": 0.8697354793548584, | |
| "eval_precision": 0.7738208157556675, | |
| "eval_recall": 0.7708333333333334, | |
| "eval_runtime": 5.3875, | |
| "eval_samples_per_second": 80.186, | |
| "eval_steps_per_second": 1.299, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 99.89, | |
| "learning_rate": 2.222222222222222e-05, | |
| "loss": 0.0987, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 99.89, | |
| "eval_accuracy": 0.7546296296296297, | |
| "eval_f1": 0.7483805060483262, | |
| "eval_loss": 0.8613447546958923, | |
| "eval_precision": 0.7517944160282697, | |
| "eval_recall": 0.7546296296296297, | |
| "eval_runtime": 5.9006, | |
| "eval_samples_per_second": 73.213, | |
| "eval_steps_per_second": 1.186, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 100.89, | |
| "eval_accuracy": 0.7569444444444444, | |
| "eval_f1": 0.7524452878233941, | |
| "eval_loss": 0.8742324113845825, | |
| "eval_precision": 0.7596693467798895, | |
| "eval_recall": 0.7569444444444444, | |
| "eval_runtime": 5.41, | |
| "eval_samples_per_second": 79.853, | |
| "eval_steps_per_second": 1.294, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 101.59, | |
| "learning_rate": 2.0370370370370372e-05, | |
| "loss": 0.1063, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 101.89, | |
| "eval_accuracy": 0.7754629629629629, | |
| "eval_f1": 0.771150415023082, | |
| "eval_loss": 0.8497992157936096, | |
| "eval_precision": 0.7807047130932955, | |
| "eval_recall": 0.7754629629629629, | |
| "eval_runtime": 5.3692, | |
| "eval_samples_per_second": 80.459, | |
| "eval_steps_per_second": 1.304, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 102.89, | |
| "eval_accuracy": 0.7708333333333334, | |
| "eval_f1": 0.765482842949022, | |
| "eval_loss": 0.8556762933731079, | |
| "eval_precision": 0.7749402393139675, | |
| "eval_recall": 0.7708333333333334, | |
| "eval_runtime": 5.3853, | |
| "eval_samples_per_second": 80.218, | |
| "eval_steps_per_second": 1.3, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 103.3, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.097, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 103.89, | |
| "eval_accuracy": 0.7546296296296297, | |
| "eval_f1": 0.7526752444102988, | |
| "eval_loss": 0.8763903975486755, | |
| "eval_precision": 0.7633836255286668, | |
| "eval_recall": 0.7546296296296297, | |
| "eval_runtime": 5.3868, | |
| "eval_samples_per_second": 80.196, | |
| "eval_steps_per_second": 1.299, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 104.89, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0947, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 104.89, | |
| "eval_accuracy": 0.7615740740740741, | |
| "eval_f1": 0.7572102102626569, | |
| "eval_loss": 0.8676894903182983, | |
| "eval_precision": 0.7628127026058086, | |
| "eval_recall": 0.7615740740740741, | |
| "eval_runtime": 5.3643, | |
| "eval_samples_per_second": 80.532, | |
| "eval_steps_per_second": 1.305, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 105.89, | |
| "eval_accuracy": 0.75, | |
| "eval_f1": 0.7468928854511258, | |
| "eval_loss": 0.8909400701522827, | |
| "eval_precision": 0.7614134069792408, | |
| "eval_recall": 0.75, | |
| "eval_runtime": 5.5853, | |
| "eval_samples_per_second": 77.345, | |
| "eval_steps_per_second": 1.253, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 106.59, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.1013, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 106.89, | |
| "eval_accuracy": 0.7638888888888888, | |
| "eval_f1": 0.7580224420360193, | |
| "eval_loss": 0.8282936811447144, | |
| "eval_precision": 0.7620546282752422, | |
| "eval_recall": 0.7638888888888888, | |
| "eval_runtime": 5.2557, | |
| "eval_samples_per_second": 82.196, | |
| "eval_steps_per_second": 1.332, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 107.89, | |
| "eval_accuracy": 0.7662037037037037, | |
| "eval_f1": 0.7651182502225393, | |
| "eval_loss": 0.8471357822418213, | |
| "eval_precision": 0.7863882995143683, | |
| "eval_recall": 0.7662037037037037, | |
| "eval_runtime": 5.3523, | |
| "eval_samples_per_second": 80.713, | |
| "eval_steps_per_second": 1.308, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 108.3, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.0963, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 108.89, | |
| "eval_accuracy": 0.7592592592592593, | |
| "eval_f1": 0.755842788877039, | |
| "eval_loss": 0.8653424382209778, | |
| "eval_precision": 0.7701441521884681, | |
| "eval_recall": 0.7592592592592593, | |
| "eval_runtime": 5.2145, | |
| "eval_samples_per_second": 82.846, | |
| "eval_steps_per_second": 1.342, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 109.89, | |
| "learning_rate": 1.111111111111111e-05, | |
| "loss": 0.0874, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 109.89, | |
| "eval_accuracy": 0.7731481481481481, | |
| "eval_f1": 0.7691684134995852, | |
| "eval_loss": 0.8479176759719849, | |
| "eval_precision": 0.7834307987925804, | |
| "eval_recall": 0.7731481481481481, | |
| "eval_runtime": 5.3059, | |
| "eval_samples_per_second": 81.418, | |
| "eval_steps_per_second": 1.319, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 110.89, | |
| "eval_accuracy": 0.7638888888888888, | |
| "eval_f1": 0.7620275713301728, | |
| "eval_loss": 0.858402669429779, | |
| "eval_precision": 0.7719082893052805, | |
| "eval_recall": 0.7638888888888888, | |
| "eval_runtime": 6.7662, | |
| "eval_samples_per_second": 63.847, | |
| "eval_steps_per_second": 1.035, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 111.59, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.0876, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 111.89, | |
| "eval_accuracy": 0.7615740740740741, | |
| "eval_f1": 0.7550117078450348, | |
| "eval_loss": 0.8713568449020386, | |
| "eval_precision": 0.7600458540847742, | |
| "eval_recall": 0.7615740740740741, | |
| "eval_runtime": 5.3309, | |
| "eval_samples_per_second": 81.037, | |
| "eval_steps_per_second": 1.313, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 112.89, | |
| "eval_accuracy": 0.7731481481481481, | |
| "eval_f1": 0.77268516651141, | |
| "eval_loss": 0.8509048223495483, | |
| "eval_precision": 0.784707905641461, | |
| "eval_recall": 0.7731481481481481, | |
| "eval_runtime": 5.3741, | |
| "eval_samples_per_second": 80.385, | |
| "eval_steps_per_second": 1.303, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 113.3, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.0974, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 113.89, | |
| "eval_accuracy": 0.7685185185185185, | |
| "eval_f1": 0.7647850826351645, | |
| "eval_loss": 0.8688226342201233, | |
| "eval_precision": 0.7741100821185434, | |
| "eval_recall": 0.7685185185185185, | |
| "eval_runtime": 5.3672, | |
| "eval_samples_per_second": 80.49, | |
| "eval_steps_per_second": 1.304, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 114.89, | |
| "learning_rate": 5.555555555555555e-06, | |
| "loss": 0.0869, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 114.89, | |
| "eval_accuracy": 0.7847222222222222, | |
| "eval_f1": 0.7793954933888979, | |
| "eval_loss": 0.8590295314788818, | |
| "eval_precision": 0.7931805357527522, | |
| "eval_recall": 0.7847222222222222, | |
| "eval_runtime": 5.2639, | |
| "eval_samples_per_second": 82.069, | |
| "eval_steps_per_second": 1.33, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 115.89, | |
| "eval_accuracy": 0.7592592592592593, | |
| "eval_f1": 0.7578890504066979, | |
| "eval_loss": 0.8686888217926025, | |
| "eval_precision": 0.7702857997814966, | |
| "eval_recall": 0.7592592592592593, | |
| "eval_runtime": 5.3584, | |
| "eval_samples_per_second": 80.621, | |
| "eval_steps_per_second": 1.306, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 116.59, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.0877, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 116.89, | |
| "eval_accuracy": 0.7592592592592593, | |
| "eval_f1": 0.7554023755308449, | |
| "eval_loss": 0.8734990358352661, | |
| "eval_precision": 0.7698092065289778, | |
| "eval_recall": 0.7592592592592593, | |
| "eval_runtime": 5.4003, | |
| "eval_samples_per_second": 79.996, | |
| "eval_steps_per_second": 1.296, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 117.89, | |
| "eval_accuracy": 0.7546296296296297, | |
| "eval_f1": 0.7517939196845534, | |
| "eval_loss": 0.8566460609436035, | |
| "eval_precision": 0.7732181508714738, | |
| "eval_recall": 0.7546296296296297, | |
| "eval_runtime": 5.657, | |
| "eval_samples_per_second": 76.365, | |
| "eval_steps_per_second": 1.237, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 118.3, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.0883, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 118.89, | |
| "eval_accuracy": 0.7569444444444444, | |
| "eval_f1": 0.7525041374626477, | |
| "eval_loss": 0.8681396245956421, | |
| "eval_precision": 0.759078097897646, | |
| "eval_recall": 0.7569444444444444, | |
| "eval_runtime": 5.3224, | |
| "eval_samples_per_second": 81.166, | |
| "eval_steps_per_second": 1.315, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 119.89, | |
| "learning_rate": 0.0, | |
| "loss": 0.0762, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 119.89, | |
| "eval_accuracy": 0.7754629629629629, | |
| "eval_f1": 0.7676128880040883, | |
| "eval_loss": 0.8507534265518188, | |
| "eval_precision": 0.7715337787579363, | |
| "eval_recall": 0.7754629629629629, | |
| "eval_runtime": 5.389, | |
| "eval_samples_per_second": 80.163, | |
| "eval_steps_per_second": 1.299, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 119.89, | |
| "step": 720, | |
| "total_flos": 2.909790831021355e+18, | |
| "train_loss": 1.1563791312277316, | |
| "train_runtime": 2067.6252, | |
| "train_samples_per_second": 100.289, | |
| "train_steps_per_second": 0.348 | |
| } | |
| ], | |
| "max_steps": 720, | |
| "num_train_epochs": 120, | |
| "total_flos": 2.909790831021355e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |